Mastering Machine Learning with scikit-learn - Second Edition

Multi-layer perceptrons

The multi-layer perceptron is a simple ANN. Its name, however, is a misnomer. A multi-layer perceptron is not a single perceptron with multiple layers, but rather multiple layers of artificial neurons that resemble perceptrons. Multi-layer perceptrons have three or more layers of artificial neurons that form a directed, acyclic graph. Generally, each layer is fully connected to the subsequent layer; the output, or activation, of each artificial neuron in a layer is an input to every artificial neuron in the next layer. Features are input through the Input layer. The simple neurons in the input layer are connected to at least one Hidden layer. Hidden layers represents latent variables; these cannot be observed in the ...